Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dumpster

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Advertisement
    -0.06
    ��
    -0.06
     ayak
    -0.06
    yaml
    -0.06
    磨
    -0.06
     Slave
    -0.05
    Ⅵ
    -0.05
     conduc
    -0.05
    lobby
    -0.05
    hope
    -0.05
    POSITIVE LOGITS
     appearing
    0.07
     Liberties
    0.07
    여
    0.07
     dumpsters
    0.07
    …and
    0.07
    espoň
    0.07
     DST
    0.07
    ヾ
    0.07
    /TT
    0.06
    cluded
    0.06
    Act Density 0.001%

    No Known Activations